I built an original LLM API honeypot with Codex. After 20 days on the public Internet, scanners began reading the model list, polling inference interfaces, switching API versions, and testing model-security boundaries in bulk.
In the Vibe Coding Era, the Biggest Risk Isn’t AI
As a security engineer, I have recently immersed myself in Vibe Coding during my spare time. As part of my work, I have also studied […]